Former US AI Czar David Sacks says there’s no evidence that Alice Huang was a Chinese Spy
https://fixupx.com/DavidSacks/status/2121070881258504395 CNN article making the same argument https:…
AI tools, cybersecurity and development news aggregated from top sources — saved permanently with unique URLs.
Former US AI Czar David Sacks says there’s no evidence that Alice Huang was a Chinese Spy
https://fixupx.com/DavidSacks/status/2121070881258504395 CNN article making the same argument https:…
A real browser now checks every page my coding agent builds
My coding agent ships a page in minutes. It also breaks the same unwritten rules every time. No them…
My Experiment Judge Kept Saying "Undecided". Three Rows Were Missing, and Only One of Them Mattered.
A field note from the autonomous Claude Code agent I run every day on one Windows PC. The numbers co…
Collecting a Form Over the Phone: One Field at a Time, and Why
Web forms collect structured data because the browser forces structure. The phone does not. A caller…
One Business, Different Countries: Why One Answering Config Fails
A team configures an agent for their home market, it works well, and then they launch it in a second…
'"Transfer to a Human" Is Not One Feature — It Is Five'
When a vendor says "it transfers to a human", they are describing a button. When your customer exper…
What the Human Should See When an Agent Hands Off
There is a moment that decides whether an AI agent feels like a colleague or like a badly built phon…
When Should an AI Agent Hand Off to a Human? A Decision Framework
Every conference talk about AI agents contains the same diagram: the agent handles a conversation, t…
What Happens When Your Agent Has No Default Route
Every routing system eventually meets a conversation that matches nothing. Not a rare edge case — a…
Voice AI Agents on Localhost: Twilio Media Streams and OpenAI Realtime Over a Tunnel
A phone-based voice agent is the least forgiving thing you can run on a laptop. A webhook can retry.…
What our logs, Runs and paired tests say about AI bots in Japan: 8 notes, each with its data page
We run a small lab, Parallel World, that measures how AI bots and AI apps treat Japanese websites. B…
One OpenCode Config for a Multi-Model Coding Budget
If you already use OpenCode and want to assign different coding tasks to different model families wi…